No, we haven’t uploaded a fly yet
In the last two weeks, social media was set abuzz by claims that scientists had…
The Case for Low-Competence ASI Failure Scenarios
I think the community underinvests in the exploration of extremely-low-competence AGI/ASI failure modes and explain…
A List of Research Directions in Character Training
Thanks to Rohan Subramani, Ariana Azarbal, and Shubhorup Biswas for proposing some of the ideas…
“The AI Doc” is coming out March 26
On Thursday, March 26th, a major new AI documentary is coming out: The AI Doc:…
Helical Representations of Turn Structure in an LLM
This is adapted from my application for Neel Nanda's MATS 10.0 stream. It wasn't accepted,…
Teaching Models to Dream of Better Monitors through Monitor Sensitive Training
TL;DRWe introduce Monitor Sensitive Training (MST), a new post-training technique where we augment training data…
AI’s latest casualty – Peer Review & How to prevent more damage
TLDR: LLMs allow reviewers to outsource judgment without accountability; peer review breaks when judgment is…
Jeff Bezos reportedly wants $100 billion to buy and transform old manufacturing firms with AI
The Amazon magnate has a new project centered around acquiring industrial firms and revamping them…
Separating Prediction from Goal-Seeking
tl;dr: Mixing goal-directedness into cognitive processes that are working to truth-seek about possible futures tends…
Null Results From An Orexin RCT
Over the last few months we[1] have been doing a sleep experiment inspired by our suspicion…